Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    reference to group classifications or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insk
    -0.21
    uzey
    -0.18
    ABCDEFGHIJKLMNOP
    -0.17
    anou
    -0.17
    hm
    -0.15
     hang
    -0.15
     ************************************************************************
    -0.15
    ¼
    -0.14
    ksen
    -0.14
     ******************************************************************************↵
    -0.14
    POSITIVE LOGITS
     cardinal
    0.18
     Spark
    0.17
     Cardinal
    0.17
    Spark
    0.16
    spark
    0.15
     Exc
    0.15
    ags
    0.14
    ipa
    0.14
    -card
    0.14
    antom
    0.14
    Act Density 0.026%

    No Known Activations